Git Mailing List Archive on lore.kernel.org
 help / color / Atom feed
From: "brian m. carlson" <sandals@crustytoothpaste.net>
To: <git@vger.kernel.org>
Subject: [RFC PATCH 11/22] builtin/init-db: allow specifying hash algorithm on command line
Date: Mon, 13 Jan 2020 12:47:18 +0000
Message-ID: <20200113124729.3684846-12-sandals@crustytoothpaste.net> (raw)
In-Reply-To: <20200113124729.3684846-1-sandals@crustytoothpaste.net>

Allow the user to specify the hash algorithm on the command line by
using the --object-format option to git init.  Validate that the user is
not attempting to reinitialize a repository with a different hash
algorithm.  Ensure that if we are writing a non-SHA-1 repository that we
set the repository version to 1 and write the objectFormat extension.

Signed-off-by: brian m. carlson <sandals@crustytoothpaste.net>
---
 Documentation/git-init.txt |  7 +++++-
 builtin/clone.c            |  2 +-
 builtin/init-db.c          | 47 +++++++++++++++++++++++++++++++++-----
 cache.h                    |  3 ++-
 4 files changed, 50 insertions(+), 9 deletions(-)

diff --git a/Documentation/git-init.txt b/Documentation/git-init.txt
index 32880aafb0..adc6adfd38 100644
--- a/Documentation/git-init.txt
+++ b/Documentation/git-init.txt
@@ -10,7 +10,7 @@ SYNOPSIS
 --------
 [verse]
 'git init' [-q | --quiet] [--bare] [--template=<template_directory>]
-	  [--separate-git-dir <git dir>]
+	  [--separate-git-dir <git dir>] [--object-format=<format]
 	  [--shared[=<permissions>]] [directory]
 
 
@@ -48,6 +48,11 @@ Only print error and warning messages; all other output will be suppressed.
 Create a bare repository. If `GIT_DIR` environment is not set, it is set to the
 current working directory.
 
+--object-format=<format>::
+
+Specify the given object format (hash algorithm) for the repository.  The valid
+values are 'sha1' and (if enabled) 'sha256'.  'sha1' is the default.
+
 --template=<template_directory>::
 
 Specify the directory from which templates will be used.  (See the "TEMPLATE
diff --git a/builtin/clone.c b/builtin/clone.c
index 0fc89ae2b9..df895133b3 100644
--- a/builtin/clone.c
+++ b/builtin/clone.c
@@ -1096,7 +1096,7 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 		}
 	}
 
-	init_db(git_dir, real_git_dir, option_template, INIT_DB_QUIET);
+	init_db(git_dir, real_git_dir, option_template, GIT_HASH_UNKNOWN, INIT_DB_QUIET);
 
 	if (real_git_dir)
 		git_dir = real_git_dir;
diff --git a/builtin/init-db.c b/builtin/init-db.c
index b11f07064d..acb1fa1ad9 100644
--- a/builtin/init-db.c
+++ b/builtin/init-db.c
@@ -177,7 +177,8 @@ static int needs_work_tree_config(const char *git_dir, const char *work_tree)
 }
 
 static int create_default_files(const char *template_path,
-				const char *original_git_dir)
+				const char *original_git_dir,
+				const struct repository_format *fmt)
 {
 	struct stat st1;
 	struct strbuf buf = STRBUF_INIT;
@@ -187,6 +188,7 @@ static int create_default_files(const char *template_path,
 	int reinit;
 	int filemode;
 	struct strbuf err = STRBUF_INIT;
+	int repo_version = GIT_REPO_VERSION;
 
 	/* Just look for `init.templatedir` */
 	init_db_template_dir = NULL; /* re-set in case it was set before */
@@ -244,11 +246,18 @@ static int create_default_files(const char *template_path,
 			exit(1);
 	}
 
+	if (fmt->hash_algo != GIT_HASH_SHA1)
+		repo_version = GIT_REPO_VERSION_READ;
+
 	/* This forces creation of new config file */
 	xsnprintf(repo_version_string, sizeof(repo_version_string),
-		  "%d", GIT_REPO_VERSION);
+		  "%d", repo_version);
 	git_config_set("core.repositoryformatversion", repo_version_string);
 
+	if (fmt->hash_algo != GIT_HASH_SHA1)
+		git_config_set("extensions.objectformat",
+			       hash_algos[fmt->hash_algo].name);
+
 	/* Check filemode trustability */
 	path = git_path_buf(&buf, "config");
 	filemode = TEST_FILEMODE;
@@ -340,12 +349,26 @@ static void separate_git_dir(const char *git_dir, const char *git_link)
 	write_file(git_link, "gitdir: %s", git_dir);
 }
 
+static void validate_hash_algorithm(struct repository_format *repo_fmt, int hash)
+{
+	/*
+	 * If we already have an initialized repo, don't allow the user to
+	 * specify a different algorithm, as that could cause corruption.
+	 * Otherwise, if the user has specified one on the command line, use it.
+	 */
+	if (repo_fmt->version >= 0 && hash != GIT_HASH_UNKNOWN && hash != repo_fmt->hash_algo)
+		die(_("attempt to reinitialize repository with different hash"));
+	else if (hash != GIT_HASH_UNKNOWN)
+		repo_fmt->hash_algo = hash;
+}
+
 int init_db(const char *git_dir, const char *real_git_dir,
-	    const char *template_dir, unsigned int flags)
+	    const char *template_dir, int hash, unsigned int flags)
 {
 	int reinit;
 	int exist_ok = flags & INIT_DB_EXIST_OK;
 	char *original_git_dir = real_pathdup(git_dir, 1);
+	struct repository_format repo_fmt = REPOSITORY_FORMAT_INIT;
 
 	if (real_git_dir) {
 		struct stat st;
@@ -378,9 +401,11 @@ int init_db(const char *git_dir, const char *real_git_dir,
 	 * config file, so this will not fail.  What we are catching
 	 * is an attempt to reinitialize new repository with an old tool.
 	 */
-	check_repository_format(NULL);
+	check_repository_format(&repo_fmt);
 
-	reinit = create_default_files(template_dir, original_git_dir);
+	validate_hash_algorithm(&repo_fmt, hash);
+
+	reinit = create_default_files(template_dir, original_git_dir, &repo_fmt);
 
 	create_object_directory();
 
@@ -482,6 +507,8 @@ int cmd_init_db(int argc, const char **argv, const char *prefix)
 	const char *work_tree;
 	const char *template_dir = NULL;
 	unsigned int flags = 0;
+	const char *object_format = NULL;
+	int hash_algo = GIT_HASH_UNKNOWN;
 	const struct option init_db_options[] = {
 		OPT_STRING(0, "template", &template_dir, N_("template-directory"),
 				N_("directory from which templates will be used")),
@@ -494,6 +521,8 @@ int cmd_init_db(int argc, const char **argv, const char *prefix)
 		OPT_BIT('q', "quiet", &flags, N_("be quiet"), INIT_DB_QUIET),
 		OPT_STRING(0, "separate-git-dir", &real_git_dir, N_("gitdir"),
 			   N_("separate git dir from working tree")),
+		OPT_STRING(0, "object-format", &object_format, N_("hash"),
+			   N_("specify the hash algorithm to use")),
 		OPT_END()
 	};
 
@@ -546,6 +575,12 @@ int cmd_init_db(int argc, const char **argv, const char *prefix)
 		free(cwd);
 	}
 
+	if (object_format) {
+		hash_algo = hash_algo_by_name(object_format);
+		if (hash_algo == GIT_HASH_UNKNOWN)
+			die(_("unknown hash algorithm '%s'"), object_format);
+	}
+
 	if (init_shared_repository != -1)
 		set_shared_repository(init_shared_repository);
 
@@ -597,5 +632,5 @@ int cmd_init_db(int argc, const char **argv, const char *prefix)
 	UNLEAK(work_tree);
 
 	flags |= INIT_DB_EXIST_OK;
-	return init_db(git_dir, real_git_dir, template_dir, flags);
+	return init_db(git_dir, real_git_dir, template_dir, hash_algo, flags);
 }
diff --git a/cache.h b/cache.h
index 75f95f6f10..14321f55da 100644
--- a/cache.h
+++ b/cache.h
@@ -627,7 +627,8 @@ int path_inside_repo(const char *prefix, const char *path);
 #define INIT_DB_EXIST_OK 0x0002
 
 int init_db(const char *git_dir, const char *real_git_dir,
-	    const char *template_dir, unsigned int flags);
+	    const char *template_dir, int hash_algo,
+	    unsigned int flags);
 
 void sanitize_stdfds(void);
 int daemonize(void);

  parent reply index

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-01-13 12:47 [RFC PATCH 00/22] SHA-256 stage 4 implementation, part 1/3 brian m. carlson
2020-01-13 12:47 ` [RFC PATCH 01/22] hex: introduce parsing variants taking hash algorithms brian m. carlson
2020-01-13 12:47 ` [RFC PATCH 02/22] hex: add functions to parse hex object IDs in any algorithm brian m. carlson
2020-01-15 21:40   ` Junio C Hamano
2020-01-16  0:22     ` brian m. carlson
2020-01-13 12:47 ` [RFC PATCH 03/22] repository: require a build flag to use SHA-256 brian m. carlson
2020-01-13 12:47 ` [RFC PATCH 04/22] t: use hash-specific lookup tables to define test constants brian m. carlson
2020-01-13 12:47 ` [RFC PATCH 05/22] t6300: abstract away SHA-1-specific constants brian m. carlson
2020-01-13 12:47 ` [RFC PATCH 06/22] t6300: make hash algorithm independent brian m. carlson
2020-01-13 12:47 ` [RFC PATCH 07/22] t/helper/test-dump-split-index: initialize git repository brian m. carlson
2020-01-13 12:47 ` [RFC PATCH 08/22] t/helper: initialize repository if necessary brian m. carlson
2020-01-13 12:47 ` [RFC PATCH 09/22] t/helper: make repository tests hash independent brian m. carlson
2020-01-13 12:47 ` [RFC PATCH 10/22] setup: allow check_repository_format to read repository format brian m. carlson
2020-01-13 12:47 ` brian m. carlson [this message]
2020-01-13 12:47 ` [RFC PATCH 12/22] builtin/init-db: add environment variable for new repo hash brian m. carlson
2020-01-13 12:47 ` [RFC PATCH 13/22] init-db: move writing repo version into a function brian m. carlson
2020-01-13 12:47 ` [RFC PATCH 14/22] worktree: allow repository version 1 brian m. carlson
2020-01-13 12:47 ` [RFC PATCH 15/22] commit: use expected signature header for SHA-256 brian m. carlson
2020-01-13 12:47 ` [RFC PATCH 16/22] gpg-interface: improve interface for parsing tags brian m. carlson
2020-01-13 12:47 ` [RFC PATCH 17/22] tag: store SHA-256 signatures in a header brian m. carlson
2020-01-13 12:47 ` [RFC PATCH 18/22] fast-import: permit reading multiple marks files brian m. carlson
2020-01-13 12:47 ` [RFC PATCH 19/22] fast-import: add helper function for inserting mark object entries brian m. carlson
2020-01-13 12:47 ` [RFC PATCH 20/22] fast-import: make find_marks work on any mark set brian m. carlson
2020-01-13 12:47 ` [RFC PATCH 21/22] fast-import: add a generic function to iterate over marks brian m. carlson
2020-01-13 12:47 ` [RFC PATCH 22/22] fast-import: add options for rewriting submodules brian m. carlson

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200113124729.3684846-12-sandals@crustytoothpaste.net \
    --to=sandals@crustytoothpaste.net \
    --cc=git@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Git Mailing List Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/git/0 git/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 git git/ https://lore.kernel.org/git \
		git@vger.kernel.org
	public-inbox-index git

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.git


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git